Evidence
Quotes last checked against the live pages on October 22, 2026. A script re-fetches every page and fails when a quote disappears. Spot an error? See the corrections policy.
Research
Hidden Technical Debt in Machine Learning Systems
It is common to incur massive ongoing maintenance costs in real-world ML systems.
Supports: The canonical prior art. Names undeclared consumers, unstable data dependencies, legacy features, dead experimental codepaths, and configuration debt.
Limits: Written about production ML pipelines, before LLM agents and local model caches were common.
Context Rot: How Increasing Input Tokens Impacts LLM Performance
Model performance consistently degrades with increasing input length.
Supports: Retained context has a quality cost, not only a storage cost.
Limits: Vendor technical report, not peer reviewed. Measures input length, not staleness.
Lost in the Middle: How Language Models Use Long Contexts
Performance is often highest when relevant information occurs at the beginning or end of the input context.
Supports: Adding more context does not guarantee the model uses it.
Limits: Studies position within context, not outdated content.
Tool documentation
Migrate to a New Embedding Model
Embeddings that different models generate aren't comparable, so a migration involves more than changing a model name.
Supports: Vectors from an old model silently degrade retrieval until the old index is removed.
Limits: Covers embedding model changes. Does not cover source documents changing under an unchanged model.
At the moment, cached files are never deleted from your local directory: when you download a new revision of a branch, previous files are kept in case you need them again.
Supports: Model caches grow by default. Old revisions stay on disk.
Ollama FAQ: where are models stored
If a different directory needs to be used, set the environment variable OLLAMA_MODELS to the chosen directory.
Supports: The override variable. The same FAQ entry lists the default model location for macOS, Linux, and Windows.
By default, volumes aren't removed to prevent important data from being deleted.
Supports: A routine prune leaves volumes behind, so orphaned service data persists.
Displays information regarding the amount of disk space used by the Docker daemon.
Supports: The read-only inspect command for images, containers, volumes, and build cache.
Inspect and manage pip's wheel cache.
Supports: Inspect and purge commands for the pip cache.
It should never be necessary to clear the cache for any reason other than reclaiming disk space.
Supports: Package caches cost disk, not correctness. Treat them as low blast radius.
uv cache prune removes all unused cache entries.
Supports: A safe, periodic cleanup command exists for the uv cache.
If set_dir() is not called, default path is $TORCH_HOME/hub where environment variable $TORCH_HOME defaults to $XDG_CACHE_HOME/torch.
Supports: Where PyTorch Hub stores downloaded models. No cleanup command is documented.
When there are no more clients that require a particular version of the browser, that version is deleted.
Supports: Playwright cleans up its own browsers. Copies installed outside its control are not covered.
Claude Code settings: cleanupPeriodDays
Set how many days Claude Code keeps session transcripts and other application data before deleting them.
Supports: Agent transcripts have a retention setting. The default is 30 days.
These files are plaintext. Anything that passes through a tool is written to a transcript on disk.
Supports: Agent transcripts can retain secrets and file contents. Auto memory files are not swept. The same page documents claude purge and its --dry-run preview.